Voice interaction control method and device, smart home equipment and storage medium

Abstract

The invention discloses a voice interaction control method and device, smart home equipment and a storage medium, the smart home equipment is provided with a voice module, and the voice interaction control method comprises the following steps: in response to a voice instruction for waking up the voice module, obtaining a multi-dimensional state parameter influencing the size of noise around the smart home equipment; according to the multi-dimensional state parameter, determining an audio white space duration required by the current voice broadcast; performing blank-leaving processing on the current to-be-played audio according to the audio blank-leaving duration; and the voice module broadcasts the audio after blank leaving processing. According to the invention, the technical problem that the voice broadcast of the response wake-up voice module is not timely in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of household appliances, and particularly relates to a voice interaction control method and device, a smart home device, and a storage medium. BACKGROUND

[0002] With the maturity of voice recognition technology, smart home devices capable of voice interaction and voice control have emerged, such as a voice air conditioner. The voice air conditioner refers to an air conditioner system on which a voice module supporting voice interaction and voice control is mounted. With the increasing popularity of household central air conditioners among users, a large-screen line controller combined with voice recognition technology has a broad prospect.

[0003] When the voice module mounted on the smart home device is playing voice, the PA (Power Amplifier, audio power amplifier) of the voice module needs to be turned on after being woken up. The pop noise will be generated when the PA is turned on. In order to eliminate the pop noise generated when the PA is turned on, a fixed time length of white space processing is performed at the beginning of the audio of the voice broadcast, which will affect the response speed of the voice broadcast. SUMMARY

[0004] The embodiments of the present application provide a voice interaction control method and device, a smart home device, and a storage medium, which at least partly solve the technical problem of the slow response of the smart home device in voice broadcast in the related art.

[0005] In a first aspect of the present application, a voice interaction control method of a smart home device is provided. The smart home device has a voice module. The method comprises: in response to a voice instruction for waking up the voice module, acquiring a multi-dimensional state parameter affecting the noise size around the smart home device; determining an audio white space time length required for current voice broadcast according to the multi-dimensional state parameter; performing white space processing on the audio to be broadcast currently according to the audio white space time length, and playing the audio after the white space processing through the voice module.

[0006] In combination with the first aspect, in some embodiments, the smart home device is an air conditioner device, and the acquiring of the multi-dimensional state parameter affecting the noise size around the smart home device comprises: acquiring a target noise characteristic value representing the noise size generated by the indoor unit of the air conditioner device when the voice module is woken up; acquiring a voice characteristic value representing the sound size of the voice instruction; and acquiring a working condition parameter representing the current working condition of the air conditioner device.

[0007] In combination with the first aspect, in some embodiments, further comprising: periodically sampling the noise generated by the operation of the indoor unit at a preset sampling period when the voice module is in the wake-up state; and determining, in each sampling period, a noise feature value representing the noise generated by the operation of the indoor unit in the current sampling period according to the noise data sampled in the current sampling period.

[0008] In combination with the first aspect, in some embodiments, the obtaining the target noise feature value comprises: in response to a voice instruction for waking up the voice module, obtaining a noise feature value representing the noise generated by the operation of the indoor unit in a most recent sampling period as the target noise feature value.

[0009] In combination with the first aspect, in some embodiments, the working condition parameter representing the current working condition of the air conditioning device comprises one or more of the following: a current working mode of the air conditioning device, a current wind speed of an indoor fan, a current set temperature of the air conditioning device, and a running function.

[0010] In combination with the first aspect, in some embodiments, the determining the audio blanking time length required for the current voice broadcast according to the multi-dimensional state parameter comprises: inputting the multi-dimensional state parameter into a pre-trained time length estimation model, and predicting the audio blanking time length required for the current voice broadcast by the time length estimation model.

[0011] In combination with the first aspect, in some embodiments, the determining the audio blanking time length required for the current voice broadcast according to the multi-dimensional state parameter comprises: performing standardization processing on the multi-dimensional state parameter to obtain a standardized value of the multi-dimensional state parameter; inputting the standardized value of the multi-dimensional state parameter into a pre-trained time length estimation model, and predicting the audio blanking time length required for the current voice broadcast by the time length estimation model.

[0012] In combination with the first aspect, in some embodiments, the blanking processing of the current audio to be broadcast according to the audio blanking time length comprises: generating a blank audio segment according to the audio blanking time length; and splicing the blank audio segment to the front of the current audio to be broadcast to obtain the blanking-processed audio.

[0013] In combination with the first aspect, in some embodiments, the greater the noise around the smart home device, the shorter the audio blanking time length required for the current voice broadcast.

[0014] In a second aspect of the present application, a voice interaction control device of a smart home device is also provided, the smart home device having a voice module, and the voice interaction control device comprising: a parameter acquisition unit configured to acquire a multi-dimensional state parameter affecting the noise level around the smart home device in response to a voice instruction for waking up the voice module; a time length determination unit configured to determine an audio blanking time length required for current voice broadcast according to the multi-dimensional state parameter; a blanking processing unit configured to perform blanking processing on the current audio to be broadcast according to the audio blanking time length; and a broadcast control unit configured to broadcast the audio after blanking processing through the voice module.

[0015] In a third aspect of the present application, a smart home device is provided, comprising: a processor; and a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the voice interaction control method of the smart home device according to any one of the embodiments of the first aspect.

[0016] In a fourth aspect of the present application, a computer readable storage medium is provided, having stored thereon a computer program, which, when executed by a processor, implements the voice interaction control method of the smart home device according to any one of the embodiments of the first aspect.

[0017] The one or more technical solutions provided by the embodiments of the present application at least achieve the following technical effects or advantages:

[0018] By acquiring the multi-dimensional state parameter affecting the noise level around the smart home device, determining the audio blanking time length required for current voice broadcast according to the multi-dimensional state parameter, and performing blanking processing on the current audio to be broadcast according to the determined audio blanking time length, and broadcasting the audio after blanking processing through the voice module, the audio blanking time length for voice broadcast is dynamically adjusted according to the noise level around the smart home device, so that the audio blanking time length dynamically changes in different noise scenarios, the response speed to the voice instruction for waking up the voice module is relatively improved, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0020] Figure 1 A flowchart of a voice interaction control method of a smart home device according to some embodiments of the present application is shown;

[0021] Figure 2A control logic for a voice interaction control method for a smart home device according to some embodiments of the present invention is shown.

[0022] Figure 3 A schematic diagram of the functional modules of a voice interaction control device for a smart home device provided according to some embodiments of the present invention is shown.

[0023] Figure 4 A schematic diagram of the structure of a smart home device provided according to some embodiments of the present invention is shown. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Furthermore, in this invention, descriptions involving "first," "second," etc., are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0026] This invention provides a voice interaction control method for smart home devices, applicable to smart home devices equipped with a voice module. The smart home device can be an air conditioner, air purifier, smart speaker, or refrigerator, etc. The air conditioner can be a split-type air conditioner, a central air conditioner, or a window air conditioner. The voice module is integrated into the wired controller of the central air conditioner or into the indoor unit of the split-type air conditioner. The voice module includes a player program (software) for voice broadcasting and a PA (hardware).

[0027] like Figure 1 As shown, Figure 1 A flowchart of a voice interaction control method for a smart home device according to some embodiments of the present invention is shown. The voice interaction control method for the smart home device includes the following steps S101 to S103.

[0028] In step S101: In response to the voice command to wake up the voice module, obtain multi-dimensional state parameters that affect the noise level around the smart home device.

[0029] In some embodiments, the smart home device is an air conditioning device, and the state parameters affecting the noise level around the air conditioning device include the following multiple dimensions: the noise level generated by the indoor unit of the air conditioning device, the volume of the voice command to wake up the voice module, and various operating parameters of the air conditioning device.

[0030] In some embodiments, obtaining multidimensional state parameters that affect the noise level around the air conditioning unit includes: obtaining target noise feature values, voice feature values ​​that characterize the volume of the voice command that wakes up the voice module, and operating condition parameters that characterize the current operating condition of the air conditioning unit, wherein the target noise feature values ​​characterize the noise level generated by the indoor unit of the air conditioning unit when the voice module is woken up.

[0031] In some embodiments, operating parameters characterizing the current operating condition of the air conditioning equipment include: the current operating mode of the air conditioning equipment, the current fan speed of the indoor fan, the current set temperature of the air conditioning equipment, and the functions currently in operation. The current operating mode of the air conditioning equipment is one of the heating mode, cooling mode, air supply mode, and defrosting mode configured in the air conditioning equipment. The functions currently in operation of the air conditioning equipment are the additional functions currently in operation among the various additional functions of the air conditioning equipment, such as the fresh air function and the electric auxiliary heating function.

[0032] In some embodiments, the voice interaction control method for smart home devices provided in this invention may further include: when the voice module is in a wake-up state, periodically sampling the noise generated by the indoor unit of the air conditioner according to a preset sampling period; and in each sampling period, determining a noise feature value characterizing the noise level generated by the indoor unit during the current sampling period based on the noise data sampled in the current sampling period. The step of obtaining the target noise feature value includes: upon receiving a voice command to wake up the voice module, responding to the voice command, obtaining a noise feature value characterizing the noise level generated by the indoor unit of the air conditioner during the sampling period closest to the current time, as the target noise feature value. This allows for the acquisition of the indoor unit's operating noise for a short period before and after the user initiates the voice command. For example, with a sampling period of 10 seconds, the noise level of the indoor unit can be obtained from 5 seconds before to 5 seconds after the user initiates the voice command. The timing of noise detection is more accurate, which helps improve the accuracy of the audio pause duration used for the current voice playback.

[0033] In some embodiments, sound pressure level (SPL) can be used to measure the noise level generated by the indoor unit and the volume of voice commands. Therefore, the noise characteristic value for each sampling period is the noise SPL calculated based on the noise data collected within that sampling period, and the voice characteristic value for the user command is the voice SPL calculated based on the voice data of the user command. It is understood that the sampling period can be between 3 and 10 seconds; for example, it can be 3 seconds, 5 seconds, or 10 seconds. For instance, if the sampling period is set to 10 seconds, the noise SPL is calculated from the audio segments sampled within the 10-second time window.

[0034] In other embodiments, noise feature values ​​and speech feature values ​​may also be represented by other forms of parameter values, such as sound intensity level or sound power level.

[0035] In step S102: Determine the audio pause duration required for the current voice broadcast based on the multidimensional state parameters.

[0036] In some embodiments, determining the audio pause duration required for the current voice broadcast based on multidimensional state parameters may include: predicting the audio pause duration required for the current voice broadcast based on multidimensional state parameters and a pre-trained duration estimation model.

[0037] Understandably, a regression prediction model can be iteratively trained based on multiple sets of sample data until the convergence condition is met to obtain a duration prediction model. Each set of sample data includes sample values ​​for multiple parameter dimensions and blank duration values ​​as label values.

[0038] In some embodiments, the regression prediction model can employ a decision tree model or a fully connected neural network model. Taking the fully connected neural network model as an example, the fully connected neural network model is trained using multiple sets of sample data carrying label values, and the weight matrix and bias of the fully connected neural network model are updated until the convergence condition is met to obtain the duration prediction model.

[0039] In other embodiments, the state parameters obtained in step S101 can be standardized to obtain standardized values ​​for each state parameter. These standardized values ​​are then input into a pre-trained regression prediction model. The regression prediction model predicts the audio pause duration required for the current speech playback. The regression prediction model can refer to the following expression, which calculates the audio pause duration required for the current speech playback:

[0040]

[0041] f(w) represents the duration of audio pauses, x i w represents the standardized value of the i-th dimension state parameter. iThe parameter weight represents the parameter weight of the i-th parameter dimension, where n is the parameter dimension and θ is the parameter weight. T It is a weight matrix with n parameter dimensions, where x represents the state parameter of each dimension.

[0042] Understandably, the state parameters of each dimension are standardized to a value between 0 and the maximum whitespace duration. For example, if the maximum whitespace duration is 100ms, then the state parameters of each dimension are standardized to a value between 0 and 100.

[0043] When training the model, mean squared error can be used as the loss function. The loss function can be found by referring to the following expression:

[0044]

[0045] The loss function J(θ) is minimized through the training process, thereby obtaining a weight matrix w1, w2, ..., w with n parameter dimensions that satisfies the convergence condition. n ,in, For the i-th sample data x i The predicted value, y i Let m be the label value of the i-th sample data, and m be the number of samples.

[0046] In some embodiments, to standardize the state parameters of each dimension, a standardized mapping table can be pre-established. This table includes standardized values ​​corresponding to different parameter values ​​or different parameter ranges for each parameter dimension. Different operating modes of air conditioning equipment correspond to different standardized values; the higher the noise level of the operating mode, the smaller the standardized value. Different wind speed ranges correspond to different standardized values; the higher the wind speed value in a wind speed range, the smaller the standardized value. Different temperature ranges of the air conditioner's set temperature correspond to different standardized values; the higher the noise level in a temperature range, the smaller the standardized value. Different operating functions correspond to different standardized values; the higher the operating noise of an additional function, the smaller the standardized value. The standardized value for each parameter dimension is between 0 and 100 ms. For example, wind speed range a corresponds to a standardized value of 50 ms, wind speed range b (less than a) corresponds to a standardized value of 60 ms, and wind speed range c (less than b) corresponds to a standardized value of 100 ms. If the current wind speed of the indoor fan is in wind speed range b, then the standardized value corresponding to the current wind speed is 60 ms. In other embodiments, for continuous numerical state parameters such as the wind speed of the indoor fan and the set temperature of the air conditioning equipment, the standardized value corresponding to the state parameter can be obtained by pre-setting an inverse proportional coefficient.

[0047] Step S103: Perform blanking processing on the current audio to be played according to the audio blanking duration, and then play the blanked audio through the voice module.

[0048] In some embodiments, the current audio to be played is a response audio used to respond to the voice command that wakes up the voice module. One or more response audios may be pre-stored, such as "I am here", "I'm here", "Hey", etc. The current audio to be played is selected from the multiple pre-stored response audios.

[0049] In some embodiments, the current audio to be played is processed by leaving blank space according to the audio blank space duration, including: leaving blank space according to the audio blank space duration, and playing the processed audio through a voice module.

[0050] In some embodiments, the pre-stored audio to be played is obtained according to a voice command, and the audio to be played is processed by omitting a blank audio segment according to the audio omitting duration. This includes: generating a blank audio segment according to the audio omitting duration; and concatenating the blank audio segment before the audio to be played to obtain the omitting processed audio with the blank audio segment preceding it. After obtaining the omitting processed audio, the PA is opened, and the omitting processed audio is started to play through the player program and the PA, thereby responding to the voice command initiated by the user.

[0051] For example, if the audio pause duration is T1, a blank audio segment of duration T1 is generated and appended to the audio to be played, resulting in the paused audio. For example, if the audio pause duration required for the current voice broadcast is 50ms, a 50ms blank audio segment is generated and appended to the audio to be played, resulting in the paused audio with a 50ms pause at the beginning.

[0052] To facilitate understanding of the technical solutions provided in the embodiments of the present invention, a voice-activated air conditioner is used as an example below, with reference to... Figure 2 The present invention provides a control logic for a voice interaction control method for smart home devices:

[0053] S1: After the voice-activated air conditioner is turned on, the voice module, which is in a wake-up state, continuously collects the operating noise of the indoor unit of the voice-activated air conditioner according to the preset sampling period.

[0054] S2: Calculate the noise sound pressure level Db1 of the indoor unit's operating noise in each sampling period;

[0055] S3: The voice module detects the user's voice command to wake it up;

[0056] S4: Calculate the sound pressure level Db2 of the voice command;

[0057] S5: Obtain operating parameters that characterize the current operating status of the voice-activated air conditioner, including: current operating mode, current fan speed of the indoor fan, current set temperature, and currently running functions;

[0058] S6: Input the operating parameters representing the current operating conditions of the voice-activated air conditioner, the noise sound pressure level Db1 of the indoor unit's operating noise, and the voice sound pressure level Db2 of the voice command into the pre-trained duration prediction model, and predict the audio white space duration Dt required for the current voice broadcast through the duration prediction model.

[0059] S7: Given the audio blanking duration Dt, generate a blank audio segment and splice it with the current audio segment to be played.

[0060] S8: Open PA and play the spliced ​​audio through the player program and PA.

[0061] The audio pause duration generated through any of the above implementation methods dynamically adjusts the audio pause duration for voice broadcasts based on state parameters affecting the ambient noise level of smart home devices. This ensures that the greater the ambient noise, the shorter the audio pause duration for the next voice broadcast, and vice versa. This adapts the audio pause duration to dynamic changes in ambient noise, enabling more timely responses to user wake-up calls in noisy environments and allowing for longer pause durations to eliminate pop-up noise in quieter environments. Therefore, it improves the user experience.

[0062] Based on the same inventive concept, embodiments of the present invention also provide a voice interaction control device for smart home devices, wherein the smart home devices have a voice module, such as... Figure 3 As shown, the voice interaction control device of the smart home device includes: a parameter acquisition unit 301, used to acquire multi-dimensional state parameters affecting the noise level around the smart home device in response to a voice command to wake up the voice module; a duration determination unit 302, used to determine the audio whitespace duration required for the current voice broadcast based on the multi-dimensional state parameters; a whitespace processing unit 303, used to perform whitespace processing on the audio to be played in the current broadcast based on the audio whitespace duration; and a broadcast control unit 304, used to broadcast the whitespace-processed audio through the voice module.

[0063] In some embodiments, the smart home device is an air conditioning device, and the parameter acquisition unit 301 is used to: acquire a target noise feature value, wherein the target noise feature value represents the noise level generated by the indoor unit of the air conditioning device when the voice module is woken up; acquire a voice feature value representing the volume of the voice command; and acquire the operating condition parameter representing the current operating condition of the air conditioning device.

[0064] In some embodiments, the voice interaction control device of the smart home device further includes a periodic sampling unit, configured to: periodically sample the noise generated by the indoor unit during operation according to a preset sampling period when the voice module is in a wake-up state; and determine a noise characteristic value characterizing the magnitude of the noise generated by the indoor unit during operation in the current sampling period based on the noise data sampled in the current sampling period during each sampling period.

[0065] In some embodiments, the parameter acquisition unit 301 is configured to: in response to a voice command to wake up the voice module, acquire a noise characteristic value of the noise level generated by the indoor unit during the most recent sampling period, and use it as the target noise characteristic value.

[0066] In some embodiments, the operating condition parameters characterizing the current operating condition of the air conditioning equipment include one or more of the following: the current operating mode of the air conditioning equipment, the current fan speed of the indoor fan, the current set temperature of the air conditioning equipment, and the functions in operation.

[0067] In some embodiments, the duration determination unit 302 is configured to: input the multidimensional state parameters into a pre-trained duration prediction model, and predict the audio white space duration required for the current voice broadcast through the duration prediction model; wherein the duration prediction model is trained based on multiple sets of sample data, wherein each set of sample data includes sample values ​​of the multidimensional state parameters and duration values ​​as label values.

[0068] In other embodiments, the duration determination unit 302 is configured to: standardize the multidimensional state parameters to obtain standardized values ​​of the multidimensional state parameters; input the standardized values ​​of the multidimensional state parameters into a pre-trained duration prediction model, and predict the audio white space duration required for the current speech broadcast through the duration prediction model.

[0069] In some embodiments, the blanking processing unit 303 is configured to: generate a blank audio segment based on the audio blanking duration; and splice the blank audio segment before the current audio to be played to obtain the blanking processed audio.

[0070] The specific functions of each functional unit in the above-mentioned device have been described in detail in the voice interaction control method of smart home devices provided in some embodiments of the present invention, and will not be elaborated here.

[0071] Based on the same inventive concept, the present invention also provides a smart home device, such as... Figure 4As shown, the smart home device includes: a processor 402; and a memory 404 for storing executable instructions of the processor 402, wherein the processor 402 is configured to execute the instructions to implement the voice interaction control method of the smart home device described in any of the above embodiments.

[0072] Among them, Figure 4 In this document, a bus architecture (represented by bus 400) is used. Bus 400 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 402 and memory represented by memory 404. Bus 400 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 405 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 can be used to store data used by processor 402 during operation.

[0073] Based on the same inventive concept, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the voice interaction control method for smart home devices described in any of the above embodiments.

[0074] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0076] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0077] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0078] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0079] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A voice interaction control method of a smart home device, the method comprising: The smart home device has a voice module, and the method comprises: In response to a voice instruction for waking up the voice module, a multi-dimensional state parameter affecting the noise size around the smart home device is acquired; According to the multi-dimensional state parameter, the audio blanking time length required for the current voice broadcast is determined; According to the audio blanking time length, the current audio to be broadcast is blanked, and the audio after blanking is broadcast through the voice module.

2. The method of claim 1, wherein, The smart home device is an air conditioning device, and the multi-dimensional state parameter affecting the noise size around the smart home device comprises: Acquiring a target noise characteristic value, the target noise characteristic value representing the noise size generated by the indoor unit of the air conditioning device when the voice module is woken up; Acquiring a voice characteristic value representing the sound size of the voice instruction; and Acquiring a working condition parameter representing the current running working condition of the air conditioning device.

3. The method of claim 2, wherein, Further comprising: When the voice module is in a state of being woken up, periodically sampling the noise generated by the indoor unit according to a preset sampling period; In each sampling period, a noise characteristic value representing the noise size generated by the indoor unit in the current sampling period is determined according to the sampled noise data in the current sampling period.

4. The method of claim 3, wherein, The target noise characteristic value comprises: In response to a voice instruction for waking up the voice module, a noise characteristic value representing the noise size generated by the indoor unit in the last sampling period is acquired as the target noise characteristic value.

5. The method of claim 2, wherein, The working condition parameter representing the current running working condition of the air conditioning device comprises one or more of the following: The current working mode of the air conditioning device, the current wind speed of the indoor fan, the current set temperature of the air conditioning device, and the running function.

6. The method of claim 1, wherein, The audio blanking time length required for the current voice broadcast is determined according to the multi-dimensional state parameter, comprising: The multi-dimensional state parameter is input into a pre-trained time length estimation model, and the audio blanking time length required for the current voice broadcast is predicted by the time length estimation model.

7. The method of claim 1, wherein, The audio blanking time length required for the current voice broadcast is determined according to the multi-dimensional state parameter, comprising: The multi-dimensional state parameter is standardized to obtain a standardized value of the multi-dimensional state parameter; The standardized value of the multi-dimensional state parameter is input into a pre-trained time length estimation model, and the audio blanking time length required for the current voice broadcast is predicted by the time length estimation model.

8. The method of claim 1, wherein, The current audio to be broadcast is blanked according to the audio blanking time length, comprising: A blank audio segment is generated according to the audio blanking time length; The blank audio segment is spliced before the current audio to be broadcast to obtain the audio after blanking.

9. The method of any one of claims 1-8, wherein, The greater the noise around the smart home device, the shorter the audio blanking time length required for the current voice broadcast. 10.A voice interaction control device of a smart home device, characterized by, The smart home device has a voice module, and the voice interaction control device comprises: A parameter acquisition unit for acquiring a multi-dimensional state parameter affecting the noise size around the smart home device in response to a voice instruction for waking up the voice module; A time length determination unit for determining the audio blanking time length required for the current voice broadcast according to the multi-dimensional state parameter; A blank processing unit is configured to perform blank processing on the current audio to be played according to the audio blank duration. A playing control unit is configured to play the audio after the blank processing by the voice module.

11. A smart home device, comprising: The method comprises the following steps: A processor; A memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the voice interaction control method of the smart home device according to any one of claims 1-9.

12. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the voice interaction control method of the smart home device according to any one of claims 1-9.

Images